Map images back to grid on Spatial intelligence benchmark
98.84Correctnessgemini-3.1-pro
Evaluation results
| Method | Links | ||
|---|---|---|---|
| gemini-3.1-pro2026.05 | 98.84 | 94.5 | |
| gemini-3-flash2026.05 | 95.21 | 54.93 | |
| gpt5.12026.05 | 94.12 | 94.59 | |
| qwen3.5-plus2026.05 | 93.29 | 155.63 |
| Method | Links | ||
|---|---|---|---|
| gemini-3.1-pro2026.05 | 98.84 | 94.5 | |
| gemini-3-flash2026.05 | 95.21 | 54.93 | |
| gpt5.12026.05 | 94.12 | 94.59 | |
| qwen3.5-plus2026.05 | 93.29 | 155.63 |